On the representation of machine learning results for delirium prediction in a hospital information system in routine care

Sai Veeranki (Speaker), Dieter Hayn, Alphons Eggerth, Stefanie Jauk, Diether Kramer, Werner Leodolter, Günter Schreier

Research output: Chapter in Book or Conference ProceedingsConference Proceedings with Oral Presentationpeer-review

Abstract

Digitalisation of health care for the purpose of medi cal documentation lead to huge amounts of data, hence having an opport unity to derive knowledge and associations of different attributes recorded. Many health care events can be prevented when identified. Machine learning algorithms could identify such events but there is ambiguity in understanding the suggestio ns especially in clinical setup. In this paper we are presenting how we explain the dec ision based on random forest to health care professionals in the course of th e project predicting delirium during hospitalisation on the day of admission.
Original languageEnglish
Title of host publicationData, Informatics and Technology: An Inspiration for Improved Health Care (Serie Studies in Health Technology and Informatics)
PublisherIOS Press
Pages97-100
Number of pages4
ISBN (Print)978-1-61499-880-8
DOIs
Publication statusPublished - 2018
Event16th International Conference on Informatics, Management and Technology in Healthcare (ICIMTH 2018) -
Duration: 6 Jul 20188 Jul 2018

Conference

Conference16th International Conference on Informatics, Management and Technology in Healthcare (ICIMTH 2018)
Period6/07/188/07/18

Research Field

  • Exploration of Digital Health

Keywords

  • Electronic health records
  • machine learning
  • delirium
  • im portant features

Fingerprint

Dive into the research topics of 'On the representation of machine learning results for delirium prediction in a hospital information system in routine care'. Together they form a unique fingerprint.

Cite this